ouraclaw
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Unverifiable Dependencies & Remote Code Execution (HIGH): The skill clones a repository from an untrusted GitHub account (
https://github.com/montagao/ouraclaw.git) and executesbun install. This allows for the installation and execution of unverified third-party code during the skill's setup process.\n- Command Execution (MEDIUM): The skill relies on multiple shell commands (git,bun,ouraclaw,jq) to function. This provides a mechanism for potentially malicious code in the unverified repository to interact with the host system.\n- Indirect Prompt Injection (LOW): The skill ingests external health data via the Oura Ring API. Evidence Chain:\n - Ingestion points: Data returned by
ouraclaw scoreandouraclaw sleepcommands.\n - Boundary markers: None present to delimit API output from agent instructions.\n
- Capability inventory: Shell execution (
bun,git,jq) and file system access (project directory and.env).\n - Sanitization: No sanitization or validation of the API response is performed before processing.
Recommendations
- AI detected serious security threats
Audit Metadata